DevQuasar

-UPDATED-
4bit inference is working! The blogpost is updated with code snippet and requirements.txt
https://devquasar.com/uncategorized/all-about-amd-and-rocm/
-UPDATED-
I've played around with an MI100 and ROCm and collected my experience in a blogpost:
https://devquasar.com/uncategorized/all-about-amd-and-rocm/
Unfortunately I've could not make inference or training work with model loaded in 8bit or use BnB, but did everything else and documented my findings.

4 replies

csabakecskemeti

posted an update 16 days ago

Post

2748

Testing Training on AMD/ROCm the first time!

I've got my hands on an AMD Instinct MI100. It's about the same price used as a V100 but on paper has more TOPS (V100 14TOPS vs MI100 23TOPS) also the HBM has faster clock so the memory bandwidth is 1.2TB/s.
For quantized inference it's a beast (MI50 was also surprisingly fast)

For LORA training with this quick test I could not make the bnb config works so I'm running the FT on the fill size model.

Will share all the install, setup and setting I've learned in a blog post, together with the cooling shroud 3D design.

8 replies

csabakecskemeti

posted an update 25 days ago

Post

1621

I found if we apply the reasoning system prompt (that has been published on the NousResearch/DeepHermes-3-Llama-3-8B-Preview model card) other models are also react to it and start mimicking reasoning. Some better some worse. I've seen internal monologue and self questioning.

Here's a blogpost about it:
http://devquasar.com/ai/reasoning-system-prompt/

csabakecskemeti

posted an update about 1 month ago

Post

1863

Check out my idea:
LLmaaS - Local LLM as a Service

With LLmaaS, I propose leveraging locally running LLMs as a service, providing a standardized way for websites to access and utilize them for LLM-powered operations directly on the user’s device.

Demo, code, more detailed description.
https://devquasar.com/llmaas/
https://github.com/csabakecskemeti/LLmaaS
https://youtu.be/OOWGr8jcP5Q

Call for contributors
Join me a develop the LLmaaS proxy to make this a generic purpose tool to leverage local LLMs on web. Build in security measures.
I'm looking for help to make the proxy more generic support multiple local LLM services without any change on the HTML side.
Also looking for ideas how to make the HTML par more modular and easy to use.

4 replies

csabakecskemeti

posted an update about 1 month ago

Post

2091

I've made an uncensored version of DeepSeek-R1-Distill-Llama-8B with merge. It's passing the "say f***" censor test.
Tested with lm-evaluation-harness on standard open llm leaderboard tests + hellaswag. Scores are improved in most. Details on the model card.

Model:
DevQuasar/DevQuasar-R1-Uncensored-Llama-8B
Quants:
DevQuasar/DevQuasar-R1-Uncensored-Llama-8B-GGUF

6 replies

csabakecskemeti

posted an update about 1 month ago

Post

2321

I've run the open llm leaderboard evaluations + hellaswag on deepseek-ai/DeepSeek-R1-Distill-Llama-8B and compared to meta-llama/Llama-3.1-8B-Instruct and at first glance R1 do not beat Llama overall.

If anyone wants to double check the results are posted here:
https://github.com/csabakecskemeti/lm_eval_results

Am I made some mistake, or (at least this distilled version) not as good/better than the competition?

I'll run the same on the Qwen 7B distilled version too.

7 replies

AI & ML interests

Recent Activity

Team members 2

DevQuasar's activity